CtrlK
BlogDocsLog inGet started
Tessl Logo

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, actionable investigation playbook built around executable SQL and tool calls, with a clearly sequenced workflow and decision/recovery branches that anticipate failure modes. Its main limitation is mild verbosity in a few explanatory tables and the absence of any bundle-file offloading.

Suggestions

Consider moving the detailed `$app_version` / `$exception_releases` / `$lib_version` comparison table into a reference file and keeping only the decision rule inline, to tighten the main workflow.

Trim the prose around 'Picking the right version property' to the actionable rule (prefer `$app_version`, fall back to `$exception_releases`, avoid `$lib_version` for app-version questions) since the table already carries the detail.

A short 'Prerequisites' note stating that `execute-sql` access and (optionally) session replay are needed would let the reader gauge fit before starting Step 1.

DimensionReasoningScore

Conciseness

Mostly lean and focused on PostHog-specific knowledge Claude lacks (the `$app_version` vs `$lib_version` distinction, the `issue_id` virtual-field fallback, the ClickHouse nullable-JSONExtract gotcha); a few explanatory passages like the version-property table could be trimmed without losing clarity.

4 / 5

Actionability

Provides copy-paste-ready tool-call JSON and executable SQL for each step, covering the common cases (release breakdown, feature-flag enumeration, surrounding-events timeline, console logs, OTEL logs) with concrete, runnable patterns.

5 / 5

Workflow Clarity

Six numbered steps with explicit decision branches (sparkline shape → first breakdown) and recovery checkpoints ('If recent and earliest events look materially different ... Flag for `grouping-noisy-errors`', 'If `query-logs` returns nothing ... say so and move on'); read-only investigation, so no destructive-validation cap applies.

5 / 5

Progressive Disclosure

Well-organized into clearly headed Steps 1–6 with subsections 5a–5d and a 'Related skills' section that signals peer skills; no bundle files exist so everything is inline, which is appropriate for a workflow skill but keeps it just shy of the one-level-deep reference ideal.

4 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concise, and explicitly pairs a concrete 'what' with an explicit 'Use when...' trigger clause tied to a recognizable URL pattern. It is highly specific to the PostHog error-tracking niche with negligible conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Investigates a single PostHog error tracking issue end-to-end', 'Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ('Investigates ... Pulls ... synthesizes a hypothesis-grade summary') and when ('Use when the user provides an issue ID or pastes an issue URL ... and wants to understand the error') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers including 'issue ID', 'pastes an issue URL (`/error_tracking/<id>`)', and 'wants to understand the error'; a few common synonyms (e.g. 'exceptions', 'stack trace', 'crash') are absent, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Narrows to 'a single PostHog error tracking issue' with the URL pattern `/error_tracking/<id>`, a clear niche with distinct triggers and minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.